Scholarlink

With the rapid growth of Internet of Things (IoT) deployments, ensuring the security of these interconnected devices has become a critical concern. In this study, we propose a novel Machine Learning-based Online Network Intrusion Detection System (NIDS) specifically tailored for IoT architecture. Our approach harnesses the potential of advanced Machine Learning algorithms to overcome the limitations of conventional NIDS solutions. The primary objective of our strategy is to enhance IoT network security by swiftly identifying and responding to emerging threats. By leveraging the capabilities of Machine Learning, our NIDS can proactively detect and categorize various network intrusions, including both known and previously unidentified attacks. This proactive detection allows for real-time responses to attacks as they arise, mitigating potential damages and reducing the overall risk posed to IOT structures. The suggested NIDS also boasts the advantage of adaptability, capable of dynamically adjusting to changing IoT settings and evolving threat landscapes. By efficiently adapting to diverse network environments, our system remains effective and robust in safeguarding IoT networks against potential security breaches. Furthermore, our technology offers a strong and scalable solution to guarantee the security and integrity of IoT networks. The incorporation of Machine Learning techniques empowers the NIDS to quickly adapt to larger and more complex IoT infrastructures without compromising its performance. To evaluate the effectiveness of our proposed method, we conducted experiments using typical datasets, such as actual network traffic traces from UNSW-NB15. The outcomes of these experiments demonstrate the system's reliability in accurately identifying and categorizing different network intrusions, thereby affirming the efficacy of our Machine Learning-based NIDS for IoT architecture. Overall, our work presents a promising and innovative approach to fortify IoT network security, providing a proactive, adaptive, and scalable solution that effectively addresses the evolving challenges of safeguarding IoT structures in the face of emerging cyber threats.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Online Network Intrusion Detection System for IOT Structure Using Machine Learning Techniques

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • K. Mahalakshmi,
  • B. Jaison

摘要

With the rapid growth of Internet of Things (IoT) deployments, ensuring the security of these interconnected devices has become a critical concern. In this study, we propose a novel Machine Learning-based Online Network Intrusion Detection System (NIDS) specifically tailored for IoT architecture. Our approach harnesses the potential of advanced Machine Learning algorithms to overcome the limitations of conventional NIDS solutions. The primary objective of our strategy is to enhance IoT network security by swiftly identifying and responding to emerging threats. By leveraging the capabilities of Machine Learning, our NIDS can proactively detect and categorize various network intrusions, including both known and previously unidentified attacks. This proactive detection allows for real-time responses to attacks as they arise, mitigating potential damages and reducing the overall risk posed to IOT structures. The suggested NIDS also boasts the advantage of adaptability, capable of dynamically adjusting to changing IoT settings and evolving threat landscapes. By efficiently adapting to diverse network environments, our system remains effective and robust in safeguarding IoT networks against potential security breaches. Furthermore, our technology offers a strong and scalable solution to guarantee the security and integrity of IoT networks. The incorporation of Machine Learning techniques empowers the NIDS to quickly adapt to larger and more complex IoT infrastructures without compromising its performance. To evaluate the effectiveness of our proposed method, we conducted experiments using typical datasets, such as actual network traffic traces from UNSW-NB15. The outcomes of these experiments demonstrate the system's reliability in accurately identifying and categorizing different network intrusions, thereby affirming the efficacy of our Machine Learning-based NIDS for IoT architecture. Overall, our work presents a promising and innovative approach to fortify IoT network security, providing a proactive, adaptive, and scalable solution that effectively addresses the evolving challenges of safeguarding IoT structures in the face of emerging cyber threats.